Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1338914 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1060111 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.8206. Min Act: -0.0000

Data Index: 534885 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7804. Min Act: -0.0000

Data Index: 505636 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1277651 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6890. Min Act: -0.0000

Data Index: 41096 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6369. Min Act: -0.0000

Data Index: 540274 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6515. Min Act: -0.0000

Data Index: 778209 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1170165 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1116873 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6255. Min Act: -0.0000

Data Index: 845367 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1080393 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1066929 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1268772 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6010. Min Act: -0.0000

Data Index: 474006 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6020. Min Act: -0.0000

Data Index: 229075 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5615. Min Act: -0.0000

Data Index: 892744 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5983. Min Act: -0.0000

Data Index: 258733 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5977. Min Act: -0.0000

Data Index: 722386 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1065144 (C4 (Web Text))

Max Activating Token Index: 956